© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49729
    Prev
    Next
    INDEX
    Explanations

    مق

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ruff
    -0.08
     rall
    -0.08
     besonder
    -0.08
    ък
    -0.08
     quo
    -0.08
    ══
    -0.08
     nq
    -0.08
     kcal
    -0.08
    achtung
    -0.08
     Eck
    -0.08
    POSITIVE LOGITS
    ادی
    0.10
    وله
    0.09
    ദ്
    0.09
    ناط
    0.09
    امات
    0.08
    ദ
    0.08
    ദ്ദ
    0.08
    ிப்பு
    0.08
    દ
    0.08
    اد
    0.08
    Activations Density 0.001%

    No Known Activations